Cargando…

4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers

OBJECTIVES/GOALS: Pancreatic cysts are comprised of both precancerous mucinous lesions and non-mucinous lesions with minimal malignant potential. Our goal is to improve our ability to classify the type of cyst using a combination of novel radiomic features and cyst fluid proteolytic activity. METHOD...

Descripción completa

Detalles Bibliográficos
Autores principales: Hernandez, Sophia, Lourenco, Andre Luiz, Calabrese, Evan, York, Tyler, Glencer, Alexa, Behr, Spencer, Wang, Zhen Jane, Koay, Eugene, Craik, Charles, Kirkwood, Kimberly
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cambridge University Press 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8822985/
http://dx.doi.org/10.1017/cts.2020.417
_version_ 1784646718177935360
author Hernandez, Sophia
Lourenco, Andre Luiz
Calabrese, Evan
York, Tyler
Glencer, Alexa
Behr, Spencer
Wang, Zhen Jane
Koay, Eugene
Craik, Charles
Kirkwood, Kimberly
author_facet Hernandez, Sophia
Lourenco, Andre Luiz
Calabrese, Evan
York, Tyler
Glencer, Alexa
Behr, Spencer
Wang, Zhen Jane
Koay, Eugene
Craik, Charles
Kirkwood, Kimberly
author_sort Hernandez, Sophia
collection PubMed
description OBJECTIVES/GOALS: Pancreatic cysts are comprised of both precancerous mucinous lesions and non-mucinous lesions with minimal malignant potential. Our goal is to improve our ability to classify the type of cyst using a combination of novel radiomic features and cyst fluid proteolytic activity. METHODS/STUDY POPULATION: Preoperative pancreatic protocol CT images from 30 patients with proteolytic assay characterization, followed by surgical resection with a pathologically confirmed pancreatic cyst diagnosis between 2016-2019 will be used in this study. We will contour images using the widely available software 3D Slicer, and extract radiomic features using IBEX software. We will analyze area under the ROC curves to identify the radiomic features that best differentiate mucinous from non-mucinous cysts, and identify features to be cross validated. The predictive ability of identified radiomic features combined with proteolytic assay will be determined by performing multiple logistic regression analysis and comparing AUROC analysis. We will determine sensitivity and specificity for individual, as well as combinations of, analytes to determine the optimal classifier. RESULTS/ANTICIPATED RESULTS: We anticipate that the predictive ability, sensitivity, and specificity of utilizing radiomic features combined with proteolytic assay data will exceed the performance of any individual test. DISCUSSION/SIGNIFICANCE OF IMPACT: This work is designed to provide a predictive radiomic model that will enable us to better identify mucinous cysts that require further evaluation, and potentially prevent unnecessary surgery in other patients. Ultimately, we would like to improve the accuracy of noninvasive radiographic evaluation using radiomic markers. CONFLICT OF INTEREST DESCRIPTION: Dr. Charles Craik is a co-founder of Alaunus Biosciences, Inc.
format Online
Article
Text
id pubmed-8822985
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Cambridge University Press
record_format MEDLINE/PubMed
spelling pubmed-88229852022-02-18 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers Hernandez, Sophia Lourenco, Andre Luiz Calabrese, Evan York, Tyler Glencer, Alexa Behr, Spencer Wang, Zhen Jane Koay, Eugene Craik, Charles Kirkwood, Kimberly J Clin Transl Sci Translational Science, Policy, & Health Outcomes Science OBJECTIVES/GOALS: Pancreatic cysts are comprised of both precancerous mucinous lesions and non-mucinous lesions with minimal malignant potential. Our goal is to improve our ability to classify the type of cyst using a combination of novel radiomic features and cyst fluid proteolytic activity. METHODS/STUDY POPULATION: Preoperative pancreatic protocol CT images from 30 patients with proteolytic assay characterization, followed by surgical resection with a pathologically confirmed pancreatic cyst diagnosis between 2016-2019 will be used in this study. We will contour images using the widely available software 3D Slicer, and extract radiomic features using IBEX software. We will analyze area under the ROC curves to identify the radiomic features that best differentiate mucinous from non-mucinous cysts, and identify features to be cross validated. The predictive ability of identified radiomic features combined with proteolytic assay will be determined by performing multiple logistic regression analysis and comparing AUROC analysis. We will determine sensitivity and specificity for individual, as well as combinations of, analytes to determine the optimal classifier. RESULTS/ANTICIPATED RESULTS: We anticipate that the predictive ability, sensitivity, and specificity of utilizing radiomic features combined with proteolytic assay data will exceed the performance of any individual test. DISCUSSION/SIGNIFICANCE OF IMPACT: This work is designed to provide a predictive radiomic model that will enable us to better identify mucinous cysts that require further evaluation, and potentially prevent unnecessary surgery in other patients. Ultimately, we would like to improve the accuracy of noninvasive radiographic evaluation using radiomic markers. CONFLICT OF INTEREST DESCRIPTION: Dr. Charles Craik is a co-founder of Alaunus Biosciences, Inc. Cambridge University Press 2020-07-29 /pmc/articles/PMC8822985/ http://dx.doi.org/10.1017/cts.2020.417 Text en © The Association for Clinical and Translational Science 2020 https://creativecommons.org/licenses/by/4.0/This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Translational Science, Policy, & Health Outcomes Science
Hernandez, Sophia
Lourenco, Andre Luiz
Calabrese, Evan
York, Tyler
Glencer, Alexa
Behr, Spencer
Wang, Zhen Jane
Koay, Eugene
Craik, Charles
Kirkwood, Kimberly
4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title_full 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title_fullStr 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title_full_unstemmed 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title_short 4532 Pancreatic Cyst Risk Stratification for Early Detection of Pancreatic Cancer Using Quantitative Radiomics and Activity-Based Biomarkers
title_sort 4532 pancreatic cyst risk stratification for early detection of pancreatic cancer using quantitative radiomics and activity-based biomarkers
topic Translational Science, Policy, & Health Outcomes Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8822985/
http://dx.doi.org/10.1017/cts.2020.417
work_keys_str_mv AT hernandezsophia 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT lourencoandreluiz 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT calabreseevan 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT yorktyler 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT glenceralexa 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT behrspencer 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT wangzhenjane 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT koayeugene 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT craikcharles 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers
AT kirkwoodkimberly 4532pancreaticcystriskstratificationforearlydetectionofpancreaticcancerusingquantitativeradiomicsandactivitybasedbiomarkers